Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,re...Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,resulting in long waiting times,high carbon emissions,and other undesirable situations.It is vital to estimate incident response times quickly and accurately after traffic incidents occur for the success of incident-related planning and response activities.This study presents a model for forecasting the traffic incident duration of traffic events with high precision.The proposed model goes through a 4-stage process using various features to predict the duration of four different traffic events and presents a feature reduction approach to enable real-time data collection and prediction.In the first stage,the dataset consisting of 24,431 data points and 75 variables is prepared by data collection,merging,missing data processing and data cleaning.In the second stage,models such as Decision Trees(DT),K-Nearest Neighbour(KNN),Random Forest(RF)and Support Vector Machines(SVM)are used and hyperparameter optimisation is performed with GridSearchCV.In the third stage,feature selection and reduction are performed and real-time data are used.In the last stage,model performance with 14 variables is evaluated with metrics such as accuracy,precision,recall,F1-score,MCC,confusion matrix and SHAP.The RF model outperforms other models with an accuracy of 98.5%.The study’s prediction results demonstrate that the proposed dynamic prediction model can achieve a high level of success.展开更多
A heavy 16-day pollution episode occurred in Beijing from December 19, 2015 to January 3,2016. The mean daily AQI and PM2.5 were 240.44 and 203.6 μg/m^3. We analyzed the spatiotemporal characteristics of air pollutan...A heavy 16-day pollution episode occurred in Beijing from December 19, 2015 to January 3,2016. The mean daily AQI and PM2.5 were 240.44 and 203.6 μg/m^3. We analyzed the spatiotemporal characteristics of air pollutants, meteorology and road space speed during this period, then extended to reveal the combined effects of traffic restrictions and meteorology on urban air quality with observational data and a multivariate mutual information model. Results of spatiotemporal analysis showed that five pollution stages were identified with remarkable variation patterns based on evolution of PM2.5 concentration and weather conditions. Southern sites（DX, YDM and DS） experienced heavier pollution than northern ones（DL, CP and WL）. Stage P2 exhibited combined functions of meteorology and traffic restrictions which were delayed peak-clipping effects on PM2.5.Mutual information values of Air quality–Traffic–Meteorology（ATM–MI） revealed that additive functions of traffic restrictions, suitable relative humidity and temperature were more effective on the removal of fine particles and CO than NO2.展开更多
目前,空管各类安全管理信息化平台积累了大量非结构化文本数据,但未得到充分利用,为了挖掘空管不正常事件中潜藏的风险,研究利用收集的四千余条空管站不正常事件数据和自构建的4836个空管领域专业术语词,提出了一个基于空管专业信息词...目前,空管各类安全管理信息化平台积累了大量非结构化文本数据,但未得到充分利用,为了挖掘空管不正常事件中潜藏的风险,研究利用收集的四千余条空管站不正常事件数据和自构建的4836个空管领域专业术语词,提出了一个基于空管专业信息词抽取的双向编码器表征法和双向长短时记忆网络的深度学习模型(Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory,BERT-BiLSTM)。该模型通过对不正常事件文本进行信息抽取,过滤其中无用信息,并将双向编码器表征法(Bidirectional Encoder Representations from Transformers,BERT)模型输出的特征向量序列作为双向长短时记忆网络(Bidirectional Long Short-Term Memory,BiLSTM)的输入序列,以对空管不正常事件文本风险识别任务进行对比试验。试验结果显示,在风险识别试验中,基于空管专业信息词抽取的BERT-BiLSTM模型相比于通用领域的BERT模型,风险识别准确率提升了3百分点。可以看出该模型有效提升了空管安全信息处理能力,能够有效识别空管部门日常运行中出现的不正常事件所带来的风险,同时可以为空管安全领域信息挖掘相关任务提供基础参考。展开更多
Fostering a dynamic sports culture relies heavily on sporting events and community engagement.In the pursuit of a robust sports culture,organizing sports events and encouraging public involvement are of utmost signifi...Fostering a dynamic sports culture relies heavily on sporting events and community engagement.In the pursuit of a robust sports culture,organizing sports events and encouraging public involvement are of utmost significance.A deep comprehension of understanding how sports events shape consumer interest holds both theoretical and practical value.This study focuses on the audience of the 2022 Beijing Winter Olympics,considering both from online and offine.Through meticulously constructing a comprehensive framework that encompasses spectator experience,demonstration effect,and media influence,and collecting 679 valid surveys nationwide,it adopts the partial least squares method-structural equation model(PLS-SEM)for in-depth analysis.The study finds that the‘traffic'generated by sports events directly influences consumers'purchase intentions in three ways:spectator experience,demonstration effect,and media influence.Among these,the demonstration effect has the most significant impact,and perceived value plays a partial mediating role.Based on the findings,several practical recommendations are proposed to further unlock the cultural and economic value of large-scale sporting events.This study not only provides empirical support for understanding the mechanisms through which mega-events stimulate consumer behavior but also offers strategic insights into enhancing the social influence and commercial value of sports in the digital era.展开更多
【背景】快速、准确地识别交通扰动事件的严重程度及其潜在影响,是制定科学应对措施和优化调控策略的前提。然而,现有事件分级评价方法大多依赖于专家知识或人为经验,容易受到主观因素的干扰,限制了评价结果的客观性和有效性。【目标】...【背景】快速、准确地识别交通扰动事件的严重程度及其潜在影响,是制定科学应对措施和优化调控策略的前提。然而,现有事件分级评价方法大多依赖于专家知识或人为经验,容易受到主观因素的干扰,限制了评价结果的客观性和有效性。【目标】解决现有交通扰动事件分级评价中主观性较强、自动化水平不足的问题,实现交通扰动事件影响后果的快速、客观分级评价。【方方法法】提出一种基于遗传算法的密度峰值聚类(Genetic Algorithm-based Density Peaks Clustering,GA-DPC)方法。首先,通过识别决策值斜率变化拐点,自动确定初始聚类中心和分类簇数量;其次,构建以最大化轮廓系数Silhouette Index(SI)为目标的优化问题,利用遗传算法求解最优截断距离;最后,基于最优截断距离迭代更新聚类中心和分类簇数量,得到最终聚类结果。【数据】利用公开数据集Spiral数据集、R15数据集和ThreeCircles数据集,以及仿真交通事故和真实降雨扰动事件数据集进行测试。【结果】GA-DPC在公开测试集上的SI值和Calinski-Harabasz(CH)值均优于ADPC、传统DPC、K-means和DBSCAN等聚类算法。在交通事故事件和降雨扰动事件影响的分级评价结果中,GA-DPC同样在SI和CH值上表现出更优的性能,验证了其在不同类型交通扰动事件分级中的有效性。【应用】GA-DPC为交通管理部门提供了一种基于数据驱动的分析工具,能够快速、客观地评估各类扰动事件对交通系统的影响程度,为资源调度和应急管理策略的制定提供决策依据。展开更多
文摘Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,resulting in long waiting times,high carbon emissions,and other undesirable situations.It is vital to estimate incident response times quickly and accurately after traffic incidents occur for the success of incident-related planning and response activities.This study presents a model for forecasting the traffic incident duration of traffic events with high precision.The proposed model goes through a 4-stage process using various features to predict the duration of four different traffic events and presents a feature reduction approach to enable real-time data collection and prediction.In the first stage,the dataset consisting of 24,431 data points and 75 variables is prepared by data collection,merging,missing data processing and data cleaning.In the second stage,models such as Decision Trees(DT),K-Nearest Neighbour(KNN),Random Forest(RF)and Support Vector Machines(SVM)are used and hyperparameter optimisation is performed with GridSearchCV.In the third stage,feature selection and reduction are performed and real-time data are used.In the last stage,model performance with 14 variables is evaluated with metrics such as accuracy,precision,recall,F1-score,MCC,confusion matrix and SHAP.The RF model outperforms other models with an accuracy of 98.5%.The study’s prediction results demonstrate that the proposed dynamic prediction model can achieve a high level of success.
基金conducted as part of the project "Concentration prediction of urban air pollutants based on deep learning" funded by Doctoral scholarship program of Tsinghua Universitypartly financial support is also provided by the National Natural Science Foundation of China (Nos. 61304199 41471333)
文摘A heavy 16-day pollution episode occurred in Beijing from December 19, 2015 to January 3,2016. The mean daily AQI and PM2.5 were 240.44 and 203.6 μg/m^3. We analyzed the spatiotemporal characteristics of air pollutants, meteorology and road space speed during this period, then extended to reveal the combined effects of traffic restrictions and meteorology on urban air quality with observational data and a multivariate mutual information model. Results of spatiotemporal analysis showed that five pollution stages were identified with remarkable variation patterns based on evolution of PM2.5 concentration and weather conditions. Southern sites（DX, YDM and DS） experienced heavier pollution than northern ones（DL, CP and WL）. Stage P2 exhibited combined functions of meteorology and traffic restrictions which were delayed peak-clipping effects on PM2.5.Mutual information values of Air quality–Traffic–Meteorology（ATM–MI） revealed that additive functions of traffic restrictions, suitable relative humidity and temperature were more effective on the removal of fine particles and CO than NO2.
文摘目前,空管各类安全管理信息化平台积累了大量非结构化文本数据,但未得到充分利用,为了挖掘空管不正常事件中潜藏的风险,研究利用收集的四千余条空管站不正常事件数据和自构建的4836个空管领域专业术语词,提出了一个基于空管专业信息词抽取的双向编码器表征法和双向长短时记忆网络的深度学习模型(Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory,BERT-BiLSTM)。该模型通过对不正常事件文本进行信息抽取,过滤其中无用信息,并将双向编码器表征法(Bidirectional Encoder Representations from Transformers,BERT)模型输出的特征向量序列作为双向长短时记忆网络(Bidirectional Long Short-Term Memory,BiLSTM)的输入序列,以对空管不正常事件文本风险识别任务进行对比试验。试验结果显示,在风险识别试验中,基于空管专业信息词抽取的BERT-BiLSTM模型相比于通用领域的BERT模型,风险识别准确率提升了3百分点。可以看出该模型有效提升了空管安全信息处理能力,能够有效识别空管部门日常运行中出现的不正常事件所带来的风险,同时可以为空管安全领域信息挖掘相关任务提供基础参考。
基金The Jiangxi Provincial Social Science Planning Project“Research on the Optimization of Development Path for Ice and Snow Tourism in Jiangxi Province’s in the Digital Economy Era”(23GL25)。
文摘Fostering a dynamic sports culture relies heavily on sporting events and community engagement.In the pursuit of a robust sports culture,organizing sports events and encouraging public involvement are of utmost significance.A deep comprehension of understanding how sports events shape consumer interest holds both theoretical and practical value.This study focuses on the audience of the 2022 Beijing Winter Olympics,considering both from online and offine.Through meticulously constructing a comprehensive framework that encompasses spectator experience,demonstration effect,and media influence,and collecting 679 valid surveys nationwide,it adopts the partial least squares method-structural equation model(PLS-SEM)for in-depth analysis.The study finds that the‘traffic'generated by sports events directly influences consumers'purchase intentions in three ways:spectator experience,demonstration effect,and media influence.Among these,the demonstration effect has the most significant impact,and perceived value plays a partial mediating role.Based on the findings,several practical recommendations are proposed to further unlock the cultural and economic value of large-scale sporting events.This study not only provides empirical support for understanding the mechanisms through which mega-events stimulate consumer behavior but also offers strategic insights into enhancing the social influence and commercial value of sports in the digital era.
文摘【背景】快速、准确地识别交通扰动事件的严重程度及其潜在影响,是制定科学应对措施和优化调控策略的前提。然而,现有事件分级评价方法大多依赖于专家知识或人为经验,容易受到主观因素的干扰,限制了评价结果的客观性和有效性。【目标】解决现有交通扰动事件分级评价中主观性较强、自动化水平不足的问题,实现交通扰动事件影响后果的快速、客观分级评价。【方方法法】提出一种基于遗传算法的密度峰值聚类(Genetic Algorithm-based Density Peaks Clustering,GA-DPC)方法。首先,通过识别决策值斜率变化拐点,自动确定初始聚类中心和分类簇数量;其次,构建以最大化轮廓系数Silhouette Index(SI)为目标的优化问题,利用遗传算法求解最优截断距离;最后,基于最优截断距离迭代更新聚类中心和分类簇数量,得到最终聚类结果。【数据】利用公开数据集Spiral数据集、R15数据集和ThreeCircles数据集,以及仿真交通事故和真实降雨扰动事件数据集进行测试。【结果】GA-DPC在公开测试集上的SI值和Calinski-Harabasz(CH)值均优于ADPC、传统DPC、K-means和DBSCAN等聚类算法。在交通事故事件和降雨扰动事件影响的分级评价结果中,GA-DPC同样在SI和CH值上表现出更优的性能,验证了其在不同类型交通扰动事件分级中的有效性。【应用】GA-DPC为交通管理部门提供了一种基于数据驱动的分析工具,能够快速、客观地评估各类扰动事件对交通系统的影响程度,为资源调度和应急管理策略的制定提供决策依据。
